We are hiring an AI-Native Software Engineer in Abu Dhabi to build production-grade systems across Retrieval-Augmented Generation (RAG), Large Language Models (LLM), and Agentic AI orchestration. This full-time, onsite role (5 days from office, GST hours) requires strong Python fundamentals and hands-on experience with modern AI-native development tooling.
About the Role – Building AI-Native Production Systems
Core Focus: RAG pipelines, LLM context management, and Agentic AI orchestration
Frameworks: LangGraph, LangChain, or equivalent agent harnesses
Tooling: Cursor, Windsurf, GitHub Copilot, Claude Code, Aider, Codex CLI
Cloud Platforms: Azure, AWS, or GCP cloud-native deployment
Work Arrangement: Full-time, 5 days per week from the Abu Dhabi office, GST hours
Career Growth & Frontier AI Exposure
Strategic Location: Abu Dhabi – a fast-growing hub for applied AI and enterprise software development
Cutting-Edge Stack: Work daily with the latest AI-native coding tools and agentic frameworks
Full-Stack AI Ownership: From vector store selection to multi-agent orchestration and deployment
Career Growth: Build deep, hands-on expertise in one of the fastest-growing segments of software engineering
Position Overview
This AI-Native Software Engineer role requires strength in RAG — vector store selection, embedding strategies, hybrid search, and retrieval quality evaluation — alongside strong LLM skills in context management, prompt engineering, and system instructions. You will build Agentic AI systems using LangGraph, LangChain, or equivalent frameworks, applying agent harnesses, multi-agent orchestration, and supervisor/routing patterns, while working with strong Python fundamentals, cloud-native deployment, RESTful API design, enterprise identity/auth integration, and robust testing and CI/CD practices.
Why This Role Matters: As AI-Native Software Engineer, you build production RAG and LLM systems at the forefront of applied generative AI, design and orchestrate multi-agent systems using frameworks like LangGraph and LangChain, work daily with the newest AI-native development tools including Cursor, Copilot, and Claude Code, apply strong computer science fundamentals to real enterprise-grade cloud deployments, and gain deep, hands-on experience in one of the most in-demand engineering specializations of 2026.
Key Responsibilities
Retrieval-Augmented Generation (RAG)
- Select and configure vector stores for optimal retrieval performance
- Design embedding strategies and hybrid search approaches
- Evaluate and improve retrieval quality across production systems
LLM Engineering
- Manage context windows and optimize prompt engineering strategies
- Design and refine system instructions for reliable LLM behavior
Agentic AI Development
- Build agentic systems using LangGraph, LangChain, or equivalent frameworks
- Implement agent harnesses, multi-agent orchestration, and supervisor/routing patterns
Software Engineering & Deployment
- Apply strong Python mastery and computer science fundamentals to production code
- Deploy cloud-native systems on Azure, AWS, or GCP
- Design RESTful APIs and integrate enterprise identity/auth systems
- Build automated test suites with adversarial and edge-case coverage as part of CI/CD
Qualifications & Requirements
Core Technical Requirements
- Strong in RAG: vector store selection, embedding strategies, hybrid search, retrieval quality evaluation
- Strong in LLM: context management, prompt engineering, system instructions
- Strong in Agentic AI: LangGraph, LangChain, or equivalent (agent harnesses, multi-agent orchestration, supervisor/routing)
- Strong mastery of Python and computer science fundamentals
Tooling & Infrastructure
- Hands-on experience with AI-native tooling: Cursor, Windsurf, GitHub Copilot, Claude Code, Aider, Codex CLI
- Cloud-native deployment experience (Azure, AWS, or GCP)
- RESTful API design and enterprise identity/auth integration
- Testing and CI/CD experience, including adversarial and edge-case coverage
Experience Requirements
- 1+ years of work experience with Agentic AI development
- 1+ years of work experience with Large Language Models (LLM)
- 1+ years of work experience with Python programming
About This AI-Native Engineering Opportunity
This role sits within a fast-moving AI engineering team in Abu Dhabi, building production systems across RAG, LLM, and Agentic AI. The position requires deep hands-on skill with modern AI-native tooling and frameworks, offering strong career growth for engineers who want to specialize at the leading edge of applied generative AI and agent orchestration.
Career Excellence: Build production-grade RAG, LLM, and Agentic AI systems at the forefront of applied AI engineering in Abu Dhabi.
Who Should Apply?
- LLM/RAG Engineers: With hands-on experience building retrieval and generation pipelines
- Agentic AI Developers: Skilled in LangGraph, LangChain, or similar orchestration frameworks
- Python Engineers: With strong computer science fundamentals moving into applied AI
- AI-Native Tool Power Users: Comfortable working daily with Cursor, Copilot, and Claude Code
- Cloud-Native Developers: Experienced deploying production AI systems on Azure, AWS, or GCP
Recently Opening Job👇
